# Calculate the summary statistics of median_income by province
summary_stats_income <- finalData %>%
  group_by(province) %>%
  summarise(mean_median_income = mean(median_income),
            median_median_income = median(median_income),
            sd_median_income = sd(median_income),
            min_median_income = min(median_income),
            max_median_income = max(median_income))

# Keep only the 5 rows with the maximum values of 'mean_median_income' for each province
summary_stats_income_5 <- summary_stats_income %>%
  slice_max(n = 5, order_by = mean_median_income)

# Round the summary statistics to two decimal places
summary_stats_income_5 <- summary_stats_income_5 %>%
  mutate(across(starts_with("mean_"):starts_with("max_"), ~round(., 2)))

# Set the caption
caption_text <- "Table 1: Summary Statistics of Median Income by Province"

# Print the table with caption using knitr::kable()
knitr::kable(summary_stats_income_5, caption = caption_text, align = "l") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"))

# Calculate the summary statistics of population by province
summary_stats_population <- finalData %>%
  group_by(province) %>%
  summarise(mean_population = round(mean(population), 0),
            median_population = round(median(population), 0),
            sd_population = round(sd(population), 0),
            min_population = round(min(population), 0),
            max_population = round(max(population), 0))

# Keep only the 5 rows with the maximum values of 'mean_population' for each province
summary_stats_population_5 <- summary_stats_population %>%
  slice_max(n = 5, order_by = mean_population)

# Set the caption
caption_text_population <- "Table 2: Summary Statistics of Population by Province"

# Print the table with caption using knitr::kable()
kable(summary_stats_population_5, caption = caption_text_population, align = "l")%>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"))

# Calculate the summary statistics of the number of fast food restaurants by province
summary_stats_restaurants <- finalData %>%
  group_by(province) %>%
  summarise(total_restaurants = n())

# Keep only the rows with the maximum values of 'total_restaurants'
summary_stats_restaurants_10 <- summary_stats_restaurants %>%
  slice_max(n = 10, order_by = total_restaurants)

# Rename the columns in the summary statistics table
new_column_names_restaurants <- c("Province", "Total Restaurants")

# Set the new column names
colnames(summary_stats_restaurants_10) <- new_column_names_restaurants
# Set the caption
caption_text_restaurants <- "Table 3: Summary Statistics of Fast Food Restaurants by Province"

# Print the table with caption using knitr::kable()
kable(summary_stats_restaurants_10, caption = caption_text_restaurants, align = "l") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"))

#This code calculates the total number of fast food restaurants in each province by using the n() function within the summarise() function. The resulting table, summary_stats_restaurants, provides an overview of the distribution of fast food restaurants across different provinces.

# Calculate the summary statistics of the average prop_male and prop_female in each province
summary_stats_gender <- finalData %>%
  group_by(province) %>%
  summarise(mean_prop_male = round(mean(prop_male), 2),
            mean_prop_female = round(mean(prop_female), 2))
# Rename the columns in the summary statistics table
new_column_names_gender <- c("Province", "Mean Proportion Male", "Mean Proportion Female")

# Set the new column names
colnames(summary_stats_gender) <- new_column_names_gender

# Set the caption
caption_text_gender <- "Table 4: Summary Statistics of Average Proportions of Male and Female in Each Province"

# Print the table with caption using knitr::kable()
kable(head(summary_stats_gender), caption = caption_text_gender, align = "l")  %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"))

#The code calculates summary statistics (mean, median, standard deviation, minimum, maximum) of the proportion of people living in poverty (prop_poverty) grouped by province. The resulting table, summary_stats_poverty, provides insights into the poverty levels across different provinces.

# Calculate the summary statistics of prop_poverty by province
summary_stats_poverty <- finalData %>%
  group_by(province) %>%
  summarise(mean_prop_poverty = round(mean(prop_poverty), 2),
            median_prop_poverty = round(median(prop_poverty), 2),
            sd_prop_poverty = round(sd(prop_poverty), 2),
            min_prop_poverty = round(min(prop_poverty), 2),
            max_prop_poverty = round(max(prop_poverty), 2))

# Rename the columns in the summary statistics table
new_column_names_poverty_province <- c("Province", "Mean Proportion Poverty", "Median Proportion Poverty", "St. Deviation Poverty", "Minimum Proportion Poverty", "Maximum Proportion Poverty")

# Set the new column names
colnames(summary_stats_poverty) <- new_column_names_poverty_province

# Set the caption
caption_text_poverty <- "Table 5: Summary Statistics of Proportion of People Living in Poverty by Province"

# Print the table with caption using knitr::kable()
kable(head(summary_stats_poverty, 5), caption = caption_text_poverty, align = "l") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"))

#The code calculates summary statistics (mean, median, standard deviation, minimum, maximum) of the median monthly rental cost (median_monthly_rent_cost) grouped by province. The resulting table, summary_stats_rent, provides insights into the rental cost variations across different provinces.

# Calculate the summary statistics of median_monthly_rent_cost by province
summary_stats_rent <- finalData %>%
  group_by(province) %>%
  summarise(mean_rent_cost = round(mean(median_monthly_rent_cost), 2),
            median_rent_cost = round(median(median_monthly_rent_cost), 2),
            sd_rent_cost = round(sd(median_monthly_rent_cost), 2),
            min_rent_cost = round(min(median_monthly_rent_cost), 2),
            max_rent_cost = round(max(median_monthly_rent_cost), 2))

# Rename the columns in the summary statistics table
new_column_names_rent_cost <- c("Province", "Mean Rent Cost", "Median Rent Cost", "St. Deviation Rent Cost", "Minimum Rent Cost", "Maximum Rent Cost")

# Set the new column names
colnames(summary_stats_rent) <- new_column_names_rent_cost

# Set the caption
caption_text_rent <- "Table 6: Summary Statistics of Median Monthly Rental Cost by Province"

# Print the table with caption using knitr::kable()
kable(head(summary_stats_rent, 5), caption = caption_text_rent, align = "l")  %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"))

# Calculate the median income by province
median_income_by_province <- finalData %>%
  group_by(province) %>%
  summarise(median_income = median(median_income))

# Sort the data by median income in descending order
median_income_by_province <- median_income_by_province %>%
  arrange(desc(median_income))

# Create an interactive bar plot to compare median income by province
plot_median_income <- ggplot(median_income_by_province, aes(x = reorder(province, -median_income), y = median_income)) +
  geom_bar(stat = "identity", fill = "steelblue") +
  labs(title = "Comparison of Median Income by Province",
       x = "Province",
       y = "Median Income (USD)",
       caption = "Data Source: FinalData") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

# Convert the plot to an interactive plot using plotly
interactive_plot_income_median <- ggplotly(plot_median_income)

# Display the interactive plot
interactive_plot_income_median

# This bar plot compares the median income across different provinces. The provinces are ordered based on their median income in descending order. The x-axis represents the provinces, and the y-axis represents the median income in USD. The bars are filled with a steel blue color. The plot has an appropriate title, axis labels with units of measurement, and a caption indicating the data source. The x-axis labels are angled for better readability.

# Filter the data for fast food leading brands
leading_brands <- subset(finalData, !is.na(name))$name

# Generate the word frequencies
word_freq <- table(leading_brands)

# Convert the word frequencies to a data frame
word_df <- data.frame(word = names(word_freq), freq = as.numeric(word_freq))

# Sort the data frame by frequency in descending order
word_df <- word_df[order(word_df$freq, decreasing = TRUE), ]

# Limit the number of words to 100
word_df <- head(word_df, 50)

# Create the interactive word cloud
wordcloud2(word_df, size = 1.5, color = "random-dark", backgroundColor = "white")

# Filter the data for fast food restaurants
fast_food_data <- finalData %>%
  filter(!is.na(city))

# Calculate the number of fast food restaurants in each city
city_counts <- fast_food_data %>%
  count(city)

# Sort the cities by the number of fast food restaurants in descending order
top_cities <- city_counts %>%
  arrange(desc(n)) %>%
  head(10)

# Create a bar plot of the top 10 cities with the highest fast food rate
bar_plot <- ggplot(top_cities, aes(x = reorder(city, -n), y = n, fill = n)) +
  geom_bar(stat = "identity") +
  scale_fill_gradient(low = "lightblue", high = "darkblue", name = "Number of Restaurants") +
  labs(title = "Top 10 Cities with High Fast Food Rate",
       x = "City",
       y = "Number of Fast Food Restaurants",
       caption = "Data Source: FinalData") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

# Convert the plot to an interactive plot using plotly
interactive_plot <- ggplotly(bar_plot)

# Display the interactive plot
interactive_plot

# Calculate the total number of fast food restaurants by year
restaurant_trend <- finalData %>%
  group_by(year) %>%
  summarise(total_restaurants = n())

# Create an interactive line plot to show the trend of fast food restaurants over the years
plot_restaurant_trend <- ggplot(restaurant_trend, aes(x = year, y = total_restaurants)) +
  geom_line(color = "steelblue", size = 1.5) +
  labs(title = "Trend of Fast Food Restaurants Over the Years",
       x = "Year",
       y = "Total Restaurants",
       caption = "Data Source: FinalData") +
  theme_bw()

# Convert the plot to an interactive plot using plotly
interactive_plot_restaurant_trend <- ggplotly(plot_restaurant_trend)

# Display the interactive plot
interactive_plot_restaurant_trend

# Create the box plot with rotated x-axis labels
plot_median_income <- ggplot(finalData, aes(x = province, y = median_income)) +
  geom_boxplot(fill = "lightblue") +
  labs(title = "Distribution of Median Income by Province",
       x = "Province",
       y = "Median Income",
       caption = "Data Source: FinalData") +
  theme_bw() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

# Convert the plot to an interactive plot using plotly
interactive_plot_median_income <- ggplotly(plot_median_income)

# Display the interactive plot
interactive_plot_median_income

# Calculate the proportion of people in poverty by province
poverty_data <- finalData %>%
  group_by(province) %>%
  summarise(prop_poverty = mean(prop_poverty),
            total_restaurants = n_distinct(name))

# Create an interactive scatter plot
scatter_plot <- ggplot(poverty_data, aes(x = prop_poverty, y = total_restaurants)) +
  geom_point(color = "steelblue") +
  labs(title = "Relationship between Poverty and Fast Food Restaurants",
       x = "Proportion of People in Poverty",
       y = "Total Number of Fast Food Restaurants",
       caption = "Data Source: FinalData") +
  theme_bw()

# Convert the plot to an interactive plot using plotly
interactive_plot_poverty <- ggplotly(scatter_plot)

# Display the interactive plot
interactive_plot_poverty

# Calculate the total number of fast food restaurants per province
restaurants_per_province <- finalData %>%
  group_by(province) %>%
  summarise(total_restaurants = n_distinct(name))

# Convert the province names to state abbreviations
state_abbreviations <- state.abb[match(restaurants_per_province$province, state.name)]
restaurants_per_province$state <- state_abbreviations

# Add state names to the data frame
restaurants_per_province$state_name <- state.name[match(restaurants_per_province$state, state.abb)]

# Create the plotly object
plotly_map <- plot_usmap(data = restaurants_per_province, values = "total_restaurants", color = "black") +
  labs(title = "Number of Fast Food Restaurants per Province",
       fill = "Total Restaurants",
       caption = "Data Source: FinalData") +
  scale_fill_continuous(name = "Total Restaurants") +
  theme(legend.position = "right")

# Convert the plot to an interactive plot using plotly
interactive_plot_usmap <- ggplotly(plotly_map, tooltip = c("state_name", "total_restaurants"),
                             text = c("state_name", "total_restaurants"))

# Display the interactive plot
interactive_plot_usmap